Multimedia quality evaluation method, device, equipment and storage medium

Abstract

The invention discloses a multimedia quality evaluation method, a device, equipment and a storage medium. The multimedia quality evaluation method comprises the steps of obtaining feature data of to-be-evaluated multimedia as training data; the feature data are data captured according to the configuration parameters in the transmission process of the to-be-evaluated multimedia; training each single evaluation model according to the corresponding available training data, and combining the single evaluation models as a combined evaluation system; and inputting the feature data into a combination evaluation system, and outputting a final score based on the combination evaluation system. The data captured according to the configuration parameters in the transmission process of the to-be-evaluated multimedia are acquired as the training data, the evaluation model is trained online, the tedious process of offline data training and redeployment is not needed, the flexibility of model training is improved. Compared with the method for evaluating the multimedia quality by using a single evaluation model, the quality score is output in a combined evaluation system mode, so that the quality of the multimedia can be reflected more truly.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a multimedia quality evaluation method, device, equipment and storage medium. Background technique [0002] With the development of network technology and the arrival of the multimedia era, various multimedia processing and communication technologies emerge in an endless stream. Due to the large amount of multimedia business data, high real-time requirements, and strong user sensitivity, in order to ensure a good quality of service experience, multimedia quality Evaluation is of great significance to manufacturers and operators of multimedia communication equipment. [0003] In the prior art, a machine learning model is usually used to evaluate the quality of multimedia. For example, multiple feature data in the multimedia are designated as parameter indicators, and the multimedia and corresponding parameter indicators are input into the machine learning model, and...

AI Technical Summary

Problems solved by technology

[0004] However, the above-mentioned machine learning models are usually trained offline and then deployed online. When the feature data input in real time changes, its evaluation ability will also decrease, so the adaptability and flexibility are poor.

Images